© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 493
    Prev
    Next
    INDEX
    Explanations

    items related to measurement tools and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    commonality or typicality

    np_acts-logits-general · gemini-2.0-flash

    usually or typically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     তারিখ
    -0.54
    γη
    -0.52
     xuyên
    -0.48
    براير
    -0.48
    FormTagHelper
    -0.47
     Bourgoin
    -0.47
     noce
    -0.45
    <bos>
    -0.45
    orsese
    -0.44
    MessageTagHelper
    -0.42
    POSITIVE LOGITS
     usually
    1.57
    usually
    1.51
    Usually
    1.49
     typically
    1.47
     Usually
    1.44
    typically
    1.42
    Typically
    1.41
     Typically
    1.32
     généralement
    1.30
     biasanya
    1.25
    Activations Density 0.731%

    No Known Activations